Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66bfe4e55a8a97ea109c8d572ad762f6f2db86f16e6dd85a9f87a91a632b415a
+oid sha256:384b38b89b8c676dce04baa48b7f1ff8bccb04c9f7b7430dafa279ba0aa36dbe
 size 9864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7383f2260b87fc3aa07075110236e7b67de49c7526d3af6367d9bbc96343eefc
+oid sha256:b98ba7d68c6674c98b4d3271b759e7ce03436210f3afc1a3dfd25c7d220135f6
 size 24006

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d77a65607154d70687243b396570dcaa0cf3183b4bb72f9e298cce29482a46d6
+oid sha256:835f7a12fc6b6157a727376481b40bc21b9c7d29c41ff0afea2b253d2ef83435
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a7c1078eb5a1a7c3016e3bc1b27b5075c61ea30d4750bf448abc31716e92a9c
+oid sha256:1164ae497156bc73ad6aea2c09c8b9bf103d80abc111b82a8d3df6753edffe06
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 11.5,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.13020833333333334,
+  "epoch": 0.1736111111111111,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 158.855,
       "eval_steps_per_second": 39.959,
       "step": 150
+    },
+    {
+      "epoch": 0.1388888888888889,
+      "grad_norm": 0.0001984279224416241,
+      "learning_rate": 0.00017709199943488106,
+      "loss": 23.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.14756944444444445,
+      "grad_norm": 0.000453818473033607,
+      "learning_rate": 0.00017192045245496238,
+      "loss": 23.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.15625,
+      "grad_norm": 0.00018072157399728894,
+      "learning_rate": 0.00016641313195854277,
+      "loss": 23.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.16493055555555555,
+      "grad_norm": 0.00013154753833077848,
+      "learning_rate": 0.0001605968690574869,
+      "loss": 23.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.1736111111111111,
+      "grad_norm": 0.0002983634767588228,
+      "learning_rate": 0.0001545,
+      "loss": 23.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.1736111111111111,
+      "eval_loss": 11.5,
+      "eval_runtime": 3.1403,
+      "eval_samples_per_second": 154.443,
+      "eval_steps_per_second": 38.85,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -158,7 +201,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 2
+        "early_stopping_patience_counter": 3
       }
     },
     "TrainerControl": {
@@ -167,12 +210,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3889868636160.0,
+  "total_flos": 5176517492736.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null